BMC Medical Informatics and Decision Making

Continuous adaptation of conversation aids for uterine fibroids treatment options in a four-year multi-center implementation project

Abstract Background Fibroids are non-cancerous uterine growths that can cause symptoms impacting quality of life. The breadth of treatment options allows for patient-centered preference. While conversation aids are known to facilitate shared decision making, the implementation of these aids for uterine fibroids treatments is limited. We aimed to develop two end-user-acceptable uterine fibroids conversation aids for an implementation project. Our second aim was to outline the adaptations that were made to the conversation aids as implementation occurred. Methods We used a multi-phase user-centered participatory approach to develop a text-based and picture-enhanced conversation aid for uterine fibroids. We conducted a focus group with project stakeholders and user-testing interviews with eligible individuals with symptomatic uterine fibroids. We analyzed the results of the user-testing interviews using Morville’s Honeycomb framework. Spanish translations of the conversation aids occurred in parallel with the English iterations. We documented the continuous adaptations of the conversation aids that occurred during the project using an expanded framework for reporting adaptations and modifications to evidence-based interventions (FRAME). Results The first iteration of the conversation aids was developed in December 2018. Focus group participants (n = 6) appreciated the brevity of the tools and suggested changes to the bar graphs and illustrations used in the picture-enhanced version. User-testing with interview participants (n = 9) found that both conversation aids were satisfactory, with minor changes suggested. However, during implementation, significant changes were suggested by patients, other stakeholders, and participating clinicians when they reviewed the content. The most significant changes required the addition or deletion of information about treatment options as newer research was published or as novel interventions were introduced into clinical practice. Conclusions This multi-year project revealed the necessity of continuously adapting the uterine fibroids conversation aids so they remain acceptable in an implementation and sustainability context. Therefore, it is important to seek regular user feedback and plan for the need to undertake updates and revisions to conversation aids if they are going to be acceptable for clinical use.

Decision tree model for predicting ovarian tumor malignancy based on clinical markers and preoperative circulating blood cells

Ovarian cancer is a serious malignant tumor threatening women's health. The early diagnosis and effective treatments of ovarian cancer remain inadequate, and about 70% of ovarian cancers are in advanced stages when discovered. This study aimed to use the decision tree method of artificial intelligence machine learning to build a model for predicting the benign and malignant degree of ovarian cancer patients. A total of 758 patients were included in the study. These patients were diagnosed by B-ultrasound, CT or MR. The clinicopathological features and circulating blood cell indexes were recorded and analyzed. The prediction model of benign and malignant ovarian tumors was constructed by CART decision tree, and the receiver operating characteristic (ROC) curve was drawn to evaluate the predictive value of the decision tree model. It was found that significant predictor variables included age, disease duration, patient general condition and menopausal status, ascites, tumor size, HE4, CA125, ROMA index, and blood routine related indicators (except for basophil count percentage and absolute value). In the constructed decision tree model, ROMA_after was the root node with the maximum information gain. ROMA_after, Mass size (MR/CT), HE4, CA125, platelet number, lymphocyte ratio, white blood cell count, post-menopause, hematocrit and mean platelet volume were important indicators in the decision tree model. The area under the receiver operating characteristic curve of this model for predicting benign and malignant ovarian cancer was 0.86. The decision tree model was successfully constructed based on clinical indicators and preoperative circulating blood cells, and showed better results in predicting benign and malignant ovarian cancer than alone imaging indicators or biomarkers among our data, which means that our model can more accurately predict benign and malignant ovarian cancer.

Effectiveness of evidence-based decision aids for women with pathogenic BRCA1 or BRCA2 variants in the german health care context: results from a randomized controlled trial

Abstract Background Women with pathogenic BRCA1 or BRCA2 variants are at high risk for breast and ovarian cancer. Preventive options include risk-reducing breast and ovarian surgeries and intensified breast surveillance. However, individual decision-making is often associated with decisional conflicts. Two evidence-based decision aids have recently been developed for these women (healthy or with unilateral breast cancer) for the German context to support them in their decision-making process. This study evaluated their effectiveness. Methods In a randomized controlled study, women (aged 18–70 years) with pathogenic BRCA1 or BRCA2 variants were randomly assigned 1:1 to the intervention (IG, n = 230) or control (CG, n = 220) group. All participants received usual care. After baseline survey (t0), IG participants additionally received the DAs. Follow-up surveys were at three (t1) and six (t2) months. Primary outcome was decisional conflict at t1. Secondary analyses included decision status, decision regret, knowledge on risks and preventive options, self-reported psychological symptoms, acceptability of DAs, and preparation for decision-making. Results Of 450 women recruited, 417 completed t0, 398 completed t1 and 386 completed t2. Compared to CG, IG participants had lower decisional conflict scores at t1 (p = 0.049) and t2 (p = 0.006) and higher scores for knowledge (p = 0.004), acceptability (p = 0.000), and preparation for decision-making (p < 0.01). Conclusions These DAs can help improve key parameters of decision-making in women with pathogenic BRCA1 and BRCA2 variants and, thus, provide a useful add-on to the current counseling and care concept for these women in Germany. Trial registration German Clinical Trials Register, DRKS-ID: DRKS00015823, retrospectively registered 14/06/2019.

A hybrid vision transformer with ensemble CNN framework for cervical cancer diagnosis

Cervical cancer is the leading cause of cancer-related deaths among women worldwide, necessitating early and accurate detection methods. This study introduces a hybrid framework utilizing Vision Transformers (ViT) and ensemble learning-based convolutional neural networks (CNN) models for cervical cancer classification based on Pap smear images. Two prominent datasets, Mendeley LBC and SIPaKMeD, are employed, encompassing nine distinct categories of cervical cell abnormalities. The proposed approach integrates pre-trained CNN models of DenseNet201, Xception, and InceptionResNetV2 to extract high-level features, further fused through ensemble learning. These features are then processed by the ViT-based encoder model designed for improved interpretability and accuracy. Experimental results demonstrate that the hybrid model achieves superior accuracy rates of 97.26%, a recall of 97.27%, a precision of 97.27%, and 96.70% for the F1-score on the Mendeley LBC dataset. For the SIPaKMeD dataset, there was an accuracy of 99.18%, a recall of 99.18%, a precision of 99.15%, and a 99.21% F1-score. On the combined dataset, the model outperformed individual pre-trained models with 95.10% accuracy and a 95.01% F1-score. Moreover, the framework incorporates augmentation with Explainable AI (XAI) techniques, specifically Grad-CAM, to provide transparent and interpretable diagnostic outcomes, enhancing its utility in clinical settings. This research underscores the potential of hybrid AI frameworks in revolutionizing cervical cancer diagnostics by offering accurate, efficient, and interpretable solutions.

Exploring the possibilities and limitations of customized large language model to support and improve cervical cancer screening

Abstract Background The rapid advancement of artificial intelligence, driven by Generative Pre-trained Transformers (GPT), has transformed natural language processing. Prompt engineering plays a key role in guiding model outputs effectively. Our primary objective was to explore the possibilities and limitations of a custom GPT, developed via prompt engineering, as a patient education tool, which delivers publicly available information through a user-friendly design that facilitates more effective access to cervical cancer screening knowledge. Method The system was developed using the OpenAI GPT-4 model and Python programming language, with the interface built on Streamlit for cloud-based accessibility and testing. It initially presented questions to testers for preliminary assessment. For cervical cancer-related information, we referenced medical guidelines. Iterative testing optimized the prompts for quality and relevance; techniques like context provision, question chaining, and prompt-based constraints were used. Human-in-the-loop and two independent medical doctor evaluations were employed. Additionally, system performance metrics were measured. Result The web application was tested 115 times over a three-week period in 2024, with 87 female (76%) and 28 male (24%) participants. A total of 112 users completed the user experience questionnaire. Statistical analysis showed a significant association between age and perceived personalization (p = 0.047) and between gender and system customization (p = 0.037). Younger participants reported higher engagement, though not significantly. Females valued guidance on screening schedules and early detection, while males highlighted the usefulness of information regarding HPV vaccination and its role in preventing HPV-related cancers. Independent evaluations by medical doctors demonstrated consistent assessments of the system’s responses in terms of accuracy, clarity, and usefulness. Discussion While the system demonstrates potential to enhance public health awareness and promote preventive behaviors, encouraging individuals to seek information on cervical cancer screening and HPV vaccination, its conversational capabilities remain constrained by the inherent limitations of current language model technology. Conclusions Although custom GPTs can not substitute a healthcare consultations, these tools can streamline workflows, expedite information access, and support personalized care. Further research should focus on conducting well-designed randomized controlled trials to establish definitive conclusions regarding its impact and reliability. Clinical trial number Not applicable.

Cervical cancer screening uptake and its associated factor in Sub-Sharan Africa: a machine learning approach

Cervical cancer, which includes squamous cell carcinoma and adenocarcinoma, is a leading cause of cancer-related deaths globally, particularly in low- and middle-income countries (LMICs). It is preventable through early screening, but incidence and mortality rates are significantly higher in LMICs, with 94% of deaths occurring in these regions. Poor implementation of screening programs, in addition to multiple health system barriers, leads to a high burden from cervical cancer in these countries. Projections show increasing cases and deaths due to the disease by 2030. Using machine learning instead of the usual statistical tests will incorporate the complex and non-linear relationship of factors in predicting the outcome variable. The secondary data for ten Sub-Saharan African countries were utilized from the Demographic and Health Survey, DHS, to evaluate cervical cancer screening uptake among women aged 25-49 years. During cleaning missing values and outliers were removed. Class balancing by Synthetic minority oversampling techniques (SMOT) was done and tuning hyperparameters via grid search was used in the models before splitting into training and validation sets containing 89% and 20%, respectively. The following machine learning classification algorithms were used in the study: Logistic Regression, Decision Tree Classifier, Random Forest, K-Nearest Neighbor, Gradient Boosting, AdaBoost, and Extra Trees. These algorithms were employed to predict cervical cancer screening uptake. The performance of the models was evaluated using accuracy, precision, recall, and F1 score. In this study, a cervical cancer screening uptake was predicted among 75,360 weighted samples of women from an African country, aged 25-49 with the final data for model formulation of 53,461, where the Extra Trees Classifier obtained an accuracy of 94.13%, a precision of 95.76%, recall of 94.12%, F1-score of 93.80%. Then followed Random Forest: accuracy = 93.87, precision = 99.18%. Health visits, proximity to health care, using contraceptives, residing in urban settings, and exposure to media were its most crucial predictors. The ensemble methods, such as Extra Trees and Random Forest, showed the best generalization, indicating that this work well on complex datasets and can help devise targeted intervention strategies. This study demonstrates that the ensemble machine learning models, such as Extra Trees Classifier and Random Forest, are promising in predicting cervical cancer screening uptake among African women with accuracies of 94.13% and 93.87%, respectively. Key predictors include healthcare access, sociocultural factors, media exposure, residence in urban areas, and contraceptive use. The findings emphasize the need for a reduction in care barriers and the use of family planning visits and mass media in promoting screening. These results will be validated in different populations in order to find the clinical integration via decision support systems.

Application of machine learning techniques for predicting survival in ovarian cancer

Abstract Background Ovarian cancer is the fifth leading cause of mortality among women in the United States. Ovarian cancer is also known as forgotten cancer or silent disease. The survival of ovarian cancer patients depends on several factors, including the treatment process and the prognosis. Methods The ovarian cancer patients’ dataset is compiled from the Surveillance, Epidemiology, and End Results (SEER) database. With the help of a clinician, the dataset is curated, and the most relevant features are selected. Pearson’s second coefficient of skewness test is used to evaluate the skewness of the dataset. Pearson correlation coefficient is also used to investigate the associations between features. Statistical test is utilized to evaluate the significance of the features. Six Machine Learning (ML) models, including K-Nearest Neighbors , Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), Adaptive Boosting (AdaBoost), and Extreme Gradient Boosting (XGBoost), are implemented for survival prediction in both classification and regression approaches. An interpretable method, Shapley Additive Explanations (SHAP), is applied to clarify the decision-making process and determine the importance of each feature in prediction. Additionally, DTs of the RF model are displayed to show how the model predicts the survival intervals. Results Our results show that RF (Accuracy = 88.72%, AUC = 82.38%) and XGBoost (Root Mean Squad Error (RMSE)) = 20.61%, R2 = 0.4667) have the best performance for classification and regression approaches, respectively. Furthermore, using the SHAP method along with extracted DTs of the RF model, the most important features in the dataset are identified. Histologic type ICD-O-3, chemotherapy recode, year of diagnosis, age at diagnosis, tumor stage, and grade are the most important determinant factors in survival prediction. Conclusion To the best of our knowledge, our study is the first study that develops various ML models to predict ovarian cancer patients’ survival on the SEER database in both classification and regression approaches. These ML algorithms also achieve more accurate results and outperform statistical methods. Furthermore, our study is the first study to use the SHAP method to increase confidence and transparency of the proposed models’ prediction for clinicians. Moreover, our developed models, as an automated auxiliary tool, can help clinicians to have a better understanding of the estimated survival as well as important features that affect survival.

Enhanced ovarian cancer survival prediction using temporal analysis and graph neural networks

Ovarian cancer is a formidable health challenge that demands accurate and timely survival predictions to guide clinical interventions. Existing methods, while commendable, suffer from limitations in harnessing the temporal evolution of patient data and capturing intricate interdependencies among different data elements. In this paper, we present a novel methodology which combines Temporal Analysis and Graph Neural Networks (GNNs) to significantly enhance ovarian cancer survival rate predictions. The shortcomings of current processes originate from their disability to correctly seize the complex interactions amongst diverse scientific information units in addition to the dynamic modifications that arise in a affected person`s nation over time. By combining temporal information evaluation and GNNs, our cautioned approach overcomes those drawbacks and, whilst as compared to preceding methods, yields a noteworthy 8.3% benefit in precision, 4.9% more accuracy, 5.5% more advantageous recall, and a considerable 2.9% reduction in prediction latency. Our method's Temporal Analysis factor uses longitudinal affected person information to perceive good-sized styles and tendencies that offer precious insights into the direction of ovarian cancer. Through the combination of GNNs, we offer a robust framework able to shoot complicated interactions among exclusive capabilities of scientific data, permitting the version to realize diffused dependencies that would affect survival results. Our paintings have tremendous implications for scientific practice. Prompt and correct estimation of the survival price of ovarian most cancers allows scientific experts to customize remedy regimens, manipulate assets efficiently, and provide individualized care to patients. Additionally, the interpretability of our version`s predictions promotes a collaborative method for affected person care via way of means of strengthening agreement among scientific employees and the AI-driven selection help system. The proposed approach not only outperforms existing methods but also has the possible to develop ovarian cancer treatment by providing clinicians through a reliable tool for informed decision-making. Through a fusion of Temporal Analysis and Graph Neural Networks, we conduit the gap among data-driven insights and clinical practice, proposing a capable opportunity for refining patient outcomes in ovarian cancer management operations.

Development of decision aids for female BRCA1 and BRCA2 mutation carriers in Germany to support preference-sensitive decision-making

AbstractBackgroundWomen with pathogenicBRCA1andBRCA2mutations possess a high risk of developing breast and ovarian cancer. They face difficult choices when considering preventive options. This study presents the development process of the first decision aids to support this complex decision-making process in the German healthcare system.MethodsA six-step development process based on the International Patient Decision Aid Standards was used, including a systematic literature review of existing decision aids, a topical medical literature review, preparation of the decision aids, focus group discussions with women withBRCA1/2mutations, internal and external reviews by clinical and self-help experts, and user tests. All reviews were followed by iterative revisions.ResultsNo existing decision aids were transferable to the German setting. The medical research revealed a need to develop separate decision aids for women withBRCA1/2mutations (A) without a history of cancer (previvors) and (B) with a history of unilateral breast cancer (survivors). The focus group discussions confirmed a high level of approval for the decision aids from both target groups. Additionally, previvors requested more information on risk-reducing breast surgery, risk-reducing removal of both ovaries and Fallopian tubes, and psychological aspects; survivors especially wanted more information on breast cancer on the affected side (e.g. biological parameters, treatment, and risk of recurrence).ConclusionsIn a structured process, two target-group-specific DAs for previvors/survivors withBRCA1/2mutations were developed to support decision-making on risk-adapted preventive options. These patient-oriented tools offer an important addition to existing specialist medical care in Germany.

Automatic ovarian tumors recognition system based on ensemble convolutional neural network with ultrasound imaging

Abstract Background Upon the discovery of ovarian cysts, obstetricians, gynecologists, and ultrasound examiners must address the common clinical challenge of distinguishing between benign and malignant ovarian tumors. Numerous types of ovarian tumors exist, many of which exhibit similar characteristics that increase the ambiguity in clinical diagnosis. Using deep learning technology, we aimed to develop a method that rapidly and accurately assists the different diagnosis of ovarian tumors in ultrasound images. Methods Based on deep learning method, we used ten well-known convolutional neural network models (e.g., Alexnet, GoogleNet, and ResNet) for training of transfer learning. To ensure method stability and robustness, we repeated the random sampling of the training and validation data ten times. The mean of the ten test results was set as the final assessment data. After the training process was completed, the three models with the highest ratio of calculation accuracy to time required for classification were used for ensemble learning pertaining. Finally, the interpretation results of the ensemble classifier were used as the final results. We also applied ensemble gradient-weighted class activation mapping (Grad-CAM) technology to visualize the decision-making results of the models. Results The highest mean accuracy, mean sensitivity, and mean specificity of ten single CNN models were 90.51 ± 4.36%, 89.77 ± 4.16%, and 92.00 ± 5.95%, respectively. The mean accuracy, mean sensitivity, and mean specificity of the ensemble classifier method were 92.15 ± 2.84%, 91.37 ± 3.60%, and 92.92 ± 4.00%, respectively. The performance of the ensemble classifier is better than that of a single classifier in three evaluation metrics. Moreover, the standard deviation is also better which means the ensemble classifier is more stable and robust. Conclusion From the comprehensive perspective of data quantity, data diversity, robustness of validation strategy, and overall accuracy, the proposed method outperformed the methods used in previous studies. In future studies, we will continue to increase the number of authenticated images and apply our proposed method in clinical settings to increase its robustness and reliability.

Online Cost-Effectiveness ANalysis (OCEAN): a user-friendly interface to conduct cost-effectiveness analyses for cervical cancer

Abstract Background Most cost-effectiveness analyses in the context of cervical cancer prevention involve the use of mathematical models to simulate HPV infection, cervical disease and prevention strategies. However, it is common for professionals who would need to perform these analyses to not be familiar with the models. This work introduces the Online Cost-Effectiveness ANalysis tool, featuring an easy-to-use web interface providing health professionals, researchers and decision makers involved in cervical cancer prevention programmes with a useful instrument to conduct complex cost-effectiveness analyses, which are becoming an essential tool as an approach for supporting decision-making that involves important trade-offs. Results The users can run cost-effectiveness evaluations of cervical cancer prevention strategies without deep knowledge of the underlying mathematical model or any programming language, obtaining the most relevant costs and health outcomes in a user-friendly format. The results provided by the tool are consistent with the existing literature. Conclusions Having such a tool will be an asset to the cervical cancer prevention community, providing researchers with an easy-to-use instrument to conduct cost-effectiveness analyses.

Construction of the cervical cancer common terminology for promoting semantic interoperability and utilization of Chinese clinical data

Abstract Background We aimed to build a common terminology in the domain of cervical cancer, named Cervical Cancer Common Terminology (CCCT), that will facilitate clinical data exchange, ensure quality of data and support large scale data analysis. Methods The standard concepts and relations of CCCT were collected from ICD-10-CM Chinese Version, ICD-9-PC Chinese Version, officially issued commonly used Chinese clinical terms, Chinese guidelines for diagnosis and treatment of cervical cancer and Chinese medical book Lin Qiaozhi Gynecologic Oncology. 2062 cervical cancer electronic medical records (EMRs) from 16 hospitals, belong to different regions and hospital tiers, were collected for terminology enrichment and building common terms and relations. Concepts hierarchies, terms and relationships were built using Protégé. The performance of natural language processing results was evaluated by average precision, recall, and F1-score. The usability of CCCT were evaluated by terminology coverage. Results A total of 880 standard concepts, 1182 common terms, 16 relations and 6 attributes were defined in CCCT, which organized in 6 levels and 11 classes. Initial evaluation of the natural language processing results demonstrated average precision, recall, and F1-score percentages of 96%, 72.6%, and 88.5%. The average terminology coverage for three classes of terms, clinical manifestation, treatment, and pathology, were 87.22%, 92.63%, and 89.85%, respectively. Flexible Chinese expressions exist between regions, traditions, cultures, and language habits within the country, linguistic variations in different settings and diverse translation of introduced western language terms are the main reasons of uncovered terms. Conclusions Our study demonstrated the initial results of CCCT construction. This study is an ongoing work, with the update of medical knowledge, more standard clinical concepts will be added in, and with more EMRs to be collected and analyzed, the term coverage will be continuing improved. In the future, CCCT will effectively support clinical data analysis in large scale.